© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6294
    Prev
    Next
    INDEX
    Explanations

    file paths and URLs in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    File paths or code snippets containing "/" character

    np_acts-logits-general · gemini-2.0-flash

    file paths and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſind
    -0.65
    Datuak
    -0.62
     queſta
    -0.61
    MemoryWarning
    -0.60
    躇
    -0.57
    MockBean
    -0.55
    esgue
    -0.55
     plufieurs
    -0.55
     dezelve
    -0.54
    btnut
    -0.54
    POSITIVE LOGITS
    /
    1.87
     /
    1.40
    ()/
    1.23
    -/
    1.18
    }/
    1.17
    |/
    1.16
    {}/
    1.16
    '/
    1.14
    ]/
    1.13
    /
    1.12
    Activations Density 0.396%

    No Known Activations